This is your work, valued
Seth Karten
ExpertAutonomous Agents | CS PhD @ Princeton | Former @ CMU @ Waymo | @ NSF GRFP Fellow
continual-harness. Official repository of the paper: Continual Harness: Online Adaptation for Self-Improving Foundation Agents and PokeAgent Speedrun Track 2
260pokechamp. Official repository of the spotlight ICML 2025 paper, PokeChamp: an Expert-level Minimax Language Agent.
175LLM-Economist. Official repository of the 2025 paper, LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra.
119awesome-pokemon-papers.
18tcg. Pokemon Trading Card Game Pocket App AI Simulator
12MAC. Multi-Agent emergent Communication
7sampling-based-motion-planning. PRM, PRM*, RRT, RRT* implementations in Gazebo, ROS
6pokepy-engine. Pure-Python Pokemon battle environment (Gen 9).
4concordia. A library for generative social simulation
2GameDex. GameDex - Capture gameplay for AI training
2cooler-RAFT. RAFT but cooler
1improve-base-llm-RL. Python
1AGENT-DOCS. Shell
1EmuRL. Python
1EmuRust. Rust
1